Fast two-pass adversarial code review: a Code Adversary subagent hunts the concrete bug, then a clean-context Findings Adversary subagent refutes false positives.
Plugin adversarial-review from marketplace sai in smykla-skalski/sai. Commands read from the repo's manifest — 13 days ago.
adversarial-reviewFast two-pass adversarial code review. A Code Adversary subagent red-teams a diff or PR to find the concrete bug, then a separate Findings Adversary subagent with a clean context tries to refute every finding to cut false positives. Use for routine changes where a full staff review is overkill, or a
code-adversaryAdversarial code reviewer for the adversarial-review workflow (also usable by other review workflows such as ship-it). Assumes a code change is broken and hunts the concrete bug; a blocking finding needs an executed reproduction or an explicit interleaving trace, anything less is an issue or a quest
findings-adversaryFindings adversary for the adversarial-review workflow. Red-teams a numbered list of code-review findings against the source, removing false positives, stripping the blocking label from findings without executed proof, fixing bad locations, and merging duplicates. Spawn only after a code-adversary p
Council of 27 sourced engineering and UX persona agents that review code, design docs, architecture, refactors, UI surfaces, dashboards, and strategy through opinionated lenses, then synthesize convergence, disagreement, and concrete next moves.
1 skill · 27 agents
Staff-engineer-level code review evaluating architectural alignment, failure modes, observability, security, and cross-team impact.
1 skill · 9 agents
Refactoring review through 7 sourced refactoring personas (Fowler, Uncle Bob, Feathers, Beck, Metz, Ousterhout, Tornhill): scans smells + git hotspots, synthesizes a safety-first plan, then an adversary red-teams it.
1 skill · 8 agents
Critique an implementation plan before approving execution. Persona reviewers (Skeptic, Architect, Verifier) evaluate the plan against the codebase and return an Approve/Reject/Refine verdict.
1 skill · 3 agents
Adversarial manual testing: a clean-context Test Adversary subagent runs the real product surface in isolated state and tries to break it; every reproduction is rerun before it counts.
1 skill · 1 agent
Daily AI news digest covering technical advances, business news, and engineering impact
1 skill · 1 agent
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.